# How Fast Do Signatures Learn? Statistical Theory and Applications for Path Regression

arXiv: https://arxiv.org/abs/2607.17865 · HTML: https://mlsanity.com/paper/2607.17865/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 55 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 2 of 2)

- [Neural Rough Differential Equations for Long Time Series](https://mlsanity.com/paper/2009.08295/) (2020)
- [Signature moments to characterize laws of stochastic processes](https://mlsanity.com/paper/1810.10971/) (2018)

## Abstract (arXiv)

Many prediction and decision-making problems in operations research involve path-valued covariates -- data that evolve over time -- for which path signatures have become a canonical feature representation. Their use is justified by a universal approximation theorem, but this is an existence result: it guarantees that a finite-level signature can approximate any continuous path functional, without quantifying how fast the approximation error decreases as the truncation level grows. This paper develops approximation and statistical theory for signature-based path regression. We establish an (L2) approximation rate for smooth functionals of Ito diffusions and show that it is minimax optimal. We then propagate the truncation error through three statistical learning procedures -- Signature-OLS, Signature-LASSO, and Signature-Logistic -- and establish their consistency. Three real-data applications show that signatures provide informative finite-dimensional representations of path-valued covariates and can improve prediction relative to handcrafted features, in the context of finance -- foreign exchange realized volatility forecasting from intraday price paths; energy -- battery end-of-life prediction from early diagnostic current-voltage pulse paths; and medicine -- epileptic seizure detection from short electroencephalogram windows.